Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptions of people and their actions in a park setting

    oai_token-act-pair · gpt-3.5-turbo

    social interactions in a casual setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [/
    -0.86
    !".
    -0.86
    !.
    -0.85
    !",
    -0.81
    !!!
    -0.77
    !!!!!
    -0.76
     !!
    -0.76
    Therefore
    -0.76
    !!!!
    -0.76
    iots
    -0.75
    POSITIVE LOGITS
     nervously
    0.98
     dusty
    0.97
     clipboard
    0.97
     brisk
    0.94
     neatly
    0.91
     stacks
    0.90
     scrib
    0.88
     rows
    0.88
     fluorescent
    0.86
     deft
    0.86
    Act Density 0.454%

    No Known Activations